Method, device and computer-readable medium for evaluating video conference quality

Abstract

The invention discloses a method, device and computer-readable medium for evaluating video conference quality, and belongs to the technical field of artificial intelligence. The method includes: acquiring multimodal data of a video conference, where the multimodal data includes at least two kinds of modal data; respectively encoding the multimodal data to generate a multimodal representation; performing splicing processing on the multimodal representation or Add and process to generate a fusion vector; use the fusion vector as a training sample, use multiple training samples for model training, and generate an evaluation model; obtain the multi-modal data of the video conference to be tested; use the evaluation model to predict the multi-modal data to be tested , generating quality assessment results. Therefore, the video conference quality can be objectively evaluated based on the evaluation model, the accuracy and timeliness of the video conference quality evaluation are improved, and the problem of low accuracy rate of the video conference quality evaluation in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and computer-readable medium for evaluating video conference quality. Background technique [0002] In the contemporary office process, video conferencing is gradually popularized and its importance is gradually highlighted. The quality of video conferencing directly reflects the effect of video conferencing. To this end, it is necessary to effectively evaluate the quality of video conferencing. [0003] The traditional evaluation method is carried out by questionnaire survey, which not only consumes a lot of manpower in the survey process, but also needs to design the survey content specially, and adopts a scoring system for the survey results, so the entire questionnaire survey The process is relatively subjective. Therefore, the quality of video conferencing cannot be accurately and objectively evaluated. Contents of the invention ...

AI Technical Summary

Problems solved by technology

[0003] The traditional evaluation method is carried out by questionnaire survey, which not only consumes a lot of manpower in the survey process, but also needs to design the survey content specially, and adopts a scoring system for the survey results, so the entire questionnaire survey The process is relatively subjective

Therefore, the quality of video conferencing cannot be accurately and objectively assessed

Images